53417 research outputs found
Sort by
Sound Effects in Media:A Comparative Analysis of Recorded and Synthetic Samples in Live-Action and Animation
No full textCreating sound for storytelling is crucial to establishing the environment in productions such as films, TV series and video games. This process often involves repeating, layering and recording real objects or using sound libraries, which can be time-consuming and repetitive. To address these challenges, procedural audio, also known as digital foley, offers a solution by allowing sound designers to quickly generate samples. Despite its efficiency, questions remain about the believability of synthetic samples compared to real ones. In our study, we compared synthetic samples generated by an online procedural engine and integrated them with both animated and live-action visuals. Our results indicate that procedural audio is highly effective and perceived as believable in drama and sci-fi scenes, particularly for sound models such as lasers, hits, air and rockets, whereas synthetic sounds weren’t as believable in cartoon productions when representing everyday actions. Finally, we identified specific models that needed optimisation and highlighted audio features that needed improvement with feedback from audio professionals
XFMamba: Cross-Fusion Mamba for Multi-view Medical Image Classification
No full textCompared to single-view medical image classification, using multiple views can significantly enhance predictive accuracy as it can account for the complementarity of each view while leveraging correlations between views. Existing multi-view approaches typically employ separate convolutional or transformer branches combined with simplistic feature fusion strategies. However, these approaches inadvertently disregard essential cross-view correlations, leading to suboptimal classification performance, and suffer from challenges with limited receptive field (CNNs) or quadratic computational complexity (transformers). Inspired by state space sequence models, we propose XFMamba, a pure Mamba-based cross-fusion architecture to address the challenge of multi-view medical image classification. XFMamba introduces a novel two-stage fusion strategy, facilitating the learning of single-view features and their cross-view disparity. This mechanism captures spatially long-range dependencies in each view while enhancing seamless information transfer between views. Results on three public datasets, MURA, CheXpert, and DDSM, illustrate the effectiveness of our approach across diverse multi-view medical image classification tasks, showing that it outperforms existing convolution-based and transformer-based multi-view methods. Code is available at https://github.com/XZheng0427/XFMamba
Driver Monitoring Systems: Advances, Challenges, and Future Directions in Non-Contact Sensor Technologies – A Review
Full text linkNon-contact driver monitoring systems have gained traction as non-intrusive and non-invasive methods for assessing driver state. This survey reviews camera, radar, microphone, and vehicle-based sensing modalities, examining their operational principles, recent research findings, and integration considerations. Machine learning’s central role in gaze tracking, activity recognition, vital signs monitoring, and driver state prediction, is also explored. The survey highlights key challenges including limited ecological validity, demographic bias, privacy and ethical risks, and the need for real-time performance under edge-computing constraints. It also identifies key future directions, including multimodal sensor fusion, resource-efficient deployment, and integration with automated driving systems. This survey is a scoping review based on structured database searches that maps progress in non-contact driver monitoring, prioritising the latest research in view of rapid advances in sensing hardware, computer vision, and embedded AI. The synthesised findings offer practical guidance for engineers, vehicle manufacturers, and policymakers on deploying robust, privacy-preserving, and real-time driver monitoring solutions to improve road safety
Transforming Pediatric Movement Disorders Assessment: From Expert Consensus to Collaborative Approaches
No full textNovel insights into genetic causes of childhood growth failure from patients recruited to the 100 000 Genomes Project
No full textDevelopment and testing of a novel 'Growth monitor' Smartphone App for growth monitoring and the detection of growth disorders
No full textA rare case of short stature with high total insulin like growth factor 1 (IGF-1) and a novel pregnancy-associated plasma protein A2 (PAPPA2) gene mutation
No full text
Social determinants of health in recreational nitrous oxide use: a narrative review
Full text link Nitrous oxide (N 2 O), also known as laughing gas, is a colourless, odourless gas. In recent years, recreational use of N 2 O has become increasingly common. Heavy or regular use can induce health and social harms. Social determinants of health (SDOH) are the conditions in which people are born, grow, live, work and age. SDOH influence drug misuse and health outcomes but remains underexplored in N 2 O. This narrative review examines evidence on the impacts of SDOH on health and social outcomes within the context of N 2 O use. We applied the WHO Commission on Social Determinants of Health conceptual framework to map and synthesise extracted literature. Evidence supports an intersection between socioeconomic position, mental health, social setting, health system and political factors within the context of N 2 O. Identifying and addressing these intersections between SDOH and N 2 O misuse could aid prevention efforts and improve care for those affected. Future research into the impacts of ethnicity, culture and legislative changes is now warranted. </jats:p